A method and system for psychosocial adaptation intervention for a child with a juvenile malignancy
By dynamically adjusting heart rate variability and electrodermal data in conjunction with emotion computing, social anxiety characteristics are obtained, psychological adaptation risks are predicted, and the augmented reality environment is dynamically adjusted. This solves the problem of inaccurate intervention in existing technologies and achieves precise psychosocial adaptation intervention.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV
- Filing Date
- 2026-01-16
- Publication Date
- 2026-06-05
AI Technical Summary
Existing psychosocial adaptation interventions for adolescents with malignant tumors are out of touch with their physical and physiological conditions, resulting in inaccurate timing and intensity of interventions and an inability to effectively address their unique psychosocial challenges.
By dynamically correcting heart rate variability and skin conductance data, and combining natural language and speech emotion computing, text emotion vectors and speech emotion vectors are obtained. Social anxiety characteristics are obtained based on physiological stability and cognitive engagement, and psychological adaptation risk index is predicted. Augmented reality environment parameters and task difficulty are dynamically adjusted, and common task nodes are inserted to establish a social safety zone.
It enables precise intervention based on the child's true psychological state, avoids misdiagnosis and ineffective intervention, identifies social adaptation imbalance at an early stage, reduces social failure experience, and improves willingness to participate and sense of security.
Smart Images
Figure CN122158105A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of psychological nursing technology, specifically a psychosocial adaptation intervention method and system for adolescent children with malignant tumors. Background Technology
[0002] Adolescents typically refer to those aged 10-19. Adolescent cancer patients constitute a unique group, and their psychosocial adaptation intervention techniques primarily revolve around two core areas: developmental psychology and psycho-oncology of cancer.
[0003] The uniqueness of the developmental stage: Cancer occurring during adolescence disrupts the normal psychosocial development trajectory and brings unique challenges: changes in the disease and body image, such as hair loss and surgical scars, hinder the construction of self-identity, gender identity, and body image. They are in a stage of pursuing emotional and economic independence and leaving their families, but cancer forces them to rely on their families and the medical system, resulting in impaired autonomy and decision-making power; treatment leads to interruption of studies, work stagnation, and alienation from peers, and they face social isolation and strained relationships.
[0004] Psycho-oncology is a field that specifically studies the psychological, social, functional, and behavioral impacts of cancer on patients, families, and caregivers. It advocates for psychosocial support intervention in the early stages of cancer diagnosis and treatment to alleviate suffering, improve quality of life, and promote optimal treatment outcomes. It focuses not only on physical symptoms but also on psychological distress, coping skills, health behaviors, social functioning, and cognitive impairment. Psycho-oncology emphasizes comprehensive and holistic care provided by an interdisciplinary team comprised of oncologists, nurses, social workers, and psychologists. Adolescent children with malignant tumors face not only physical suffering during treatment but also severe psychosocial adaptation problems. Existing intervention methods are disconnected from the child's real-time physical and physiological state, leading to inaccurate timing and intensity of interventions. Therefore, this invention proposes a psychosocial adaptation intervention method and system for adolescent children with malignant tumors. Summary of the Invention
[0005] To overcome the aforementioned problems in the prior art, this application provides a method and system, which adopts the following technical solution:
[0006] Firstly, this application provides a psychosocial adaptation intervention method for adolescent children with malignant tumors, including:
[0007] Based on the current clinical stage, the heart rate variability and skin conductance data are dynamically adjusted, and the emotional calculation of text and speech is performed through natural language processing to obtain the text emotion vector and the speech emotion vector.
[0008] Physiological stability indicators were obtained based on modified heart rate variability and skin conductance data; cognitive engagement was obtained based on eye-tracking data and social interaction records; and social anxiety features were obtained based on physiological stability, eye-tracking data, text emotion vectors, and voice emotion vectors.
[0009] The psychological adaptation risk index is obtained by subtracting social anxiety characteristics from the positive contributions of physiological stability and cognitive engagement, and then correcting for clinical cycle deviation factors.
[0010] Predict the gradient of the psychological adaptation risk index change within a preset time period. When the gradient of change is lower than a preset threshold, map the psychological adaptation risk index and the gradient of change to augmented reality environment parameters to achieve dynamic matching of psychological state.
[0011] The psychological adaptation risk index of children with multiple nodes is calculated based on emotional correlation. When the emotional correlation value is at the bottom of synchronization, a common task node is inserted, and the parameters of the augmented reality environment and the difficulty of the task are dynamically adjusted to achieve the establishment of a social safe zone and enhanced peer support.
[0012] Secondly, this application also provides a psychosocial adaptation intervention system for adolescent children with malignant tumors, including:
[0013] The data acquisition module is used to dynamically adjust heart rate variability and skin conductance data according to the current clinical stage, and to perform emotion calculations on text and speech using natural language to obtain text emotion vectors and speech emotion vectors.
[0014] The social anxiety feature acquisition module is used to acquire physiological stability indicators based on modified heart rate variability and skin conductance data, cognitive engagement based on eye movement data and social interaction records, and social anxiety features based on physiological stability, eye movement data, text emotion vectors and voice emotion vectors.
[0015] The psychological adaptation risk index acquisition module is used to subtract social anxiety characteristics from the positive contributions of physiological stability and cognitive engagement, and then obtain the psychological adaptation risk index through clinical cycle deviation factor correction.
[0016] The psychological state dynamic matching module is used to predict the gradient of the psychological adaptation risk index change within a preset time period. When the gradient of change is lower than a preset threshold, the psychological adaptation risk index and the gradient of change are mapped to augmented reality environment parameters to achieve dynamic matching of psychological states.
[0017] The augmented reality environment parameter dynamic adjustment module is used to calculate the emotional correlation value of the psychological adaptation risk index of children with multiple nodes. When the emotional correlation value is at the bottom synchronization, a common task node is inserted, and the augmented reality environment parameters and task difficulty are dynamically adjusted to realize the establishment of social safety zones and enhanced peer support.
[0018] Thirdly, this application provides an electronic device, comprising:
[0019] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the method as described in the first aspect.
[0020] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect.
[0021] Fifthly, this application provides a computer program that, when executed by a computer, performs the method described in the first aspect.
[0022] In one possible design, the program in the fifth aspect can be stored wholly or partially on a storage medium packaged with the processor, or it can be stored wholly or partially on a memory not packaged with the processor.
[0023] This application has the following beneficial effects:
[0024] 1. This application obtains text emotion vectors and speech emotion vectors by dynamically correcting heart rate variability and electrodermal data according to the current clinical stage and performing emotion calculations on text and speech using natural language. By dynamically correcting heart rate variability and electrodermal data according to the current clinical stage, this application can distinguish between pharmacological fatigue and psychological avoidance, avoid misdiagnosis and ineffective intervention, and ensure that psychosocial adaptation intervention is based on the real psychological state, eliminating interference from non-psychological factors caused by chemotherapy or fatigue.
[0025] 2. This application obtains physiological stability indicators based on modified heart rate variability and skin conductance data, cognitive engagement based on eye-tracking data and social interaction records, and social anxiety characteristics based on physiological stability, eye-tracking data, text emotion vectors, and speech emotion vectors. This application obtains a psychological adaptation risk index by subtracting the social anxiety characteristics from the positive contributions of physiological stability and cognitive engagement, and then correcting for this with a clinical cycle deviation factor. By obtaining this psychological adaptation risk index, this application determines whether the child's corresponding psychosocial development task is impaired or delayed.
[0026] 3. This application predicts the gradient of the psychological adaptation risk index change within a preset time period. When the gradient of change is lower than a preset threshold, the psychological adaptation risk index and the gradient of change are mapped to augmented reality environment parameters to achieve dynamic matching of psychological state. This application can trigger an early adjustment strategy through the gradient of change, providing data basis for early intervention.
[0027] 4. This application calculates the emotional correlation value of the psychological adaptation risk index of children with multiple nodes. When the emotional correlation value is at a low synchronization, a common task node is inserted, dynamically adjusting the augmented reality environment parameters and task difficulty to establish a social safe zone and enhance peer support. This application objectively quantifies the degree of emotional synchronization among multiple children by conducting correlation analysis on the psychological adaptation risk index of different children, avoiding inaccurate assessments caused by relying solely on individual subjective feedback. Simultaneously, when the emotional correlation value is below a preset threshold, it can identify social adaptation imbalances among children, providing data support for early detection of social avoidance problems and reducing the probability of social failure experiences. Intervention by inserting a common task node guides children to naturally participate in collaboration with clearly defined task objectives, helping to reduce social anxiety and increase willingness to participate and sense of security. Dynamically adjusting the augmented reality environment parameters and task difficulty ensures that collaborative tasks are within a achievable and moderately challenging range, avoiding frustration caused by differences in children's abilities. Attached Figure Description
[0028] Figure 1 This is a flowchart illustrating a psychosocial adaptation intervention method for adolescent children with malignant tumors, as described in this application.
[0029] Figure 2 This is a flowchart illustrating the text sentiment vector acquisition process according to an embodiment of this application.
[0030] Figure 3 This is a flowchart illustrating the process of obtaining speech emotion vectors according to an embodiment of this application.
[0031] Figure 4 This is a flowchart illustrating the dynamic matching of psychological states in an embodiment of this application.
[0032] Figure 5 This is a framework diagram of a psychosocial adaptation intervention system for adolescent children with malignant tumors, as described in this application. Detailed Implementation
[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.
[0034] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0035] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
[0036] Please refer to Figure 1 The flowchart provided in this application is a method for psychosocial adaptation intervention in adolescent children with malignant tumors, and its specific contents include:
[0037] Step 101: Based on the current clinical stage, dynamically adjust the heart rate variability and skin conductance data, and perform emotion calculation on text and speech using natural language to obtain text emotion vectors and speech emotion vectors.
[0038] In this application embodiment, dynamically correcting heart rate variability and electrodermal data based on the current clinical stage includes:
[0039] The system collects heart rate variability and skin conductance data in real time, labels the current clinical stage and dosing information, obtains reference values for the corresponding clinical stage from a preset clinical baseline library, calculates the offset between the real-time collected data and the reference values, generates a deviation compensation factor based on the offset, and divides the real-time heart rate variability and skin conductance data by the deviation compensation factor to obtain the corrected heart rate variability and skin conductance data.
[0040] It should be noted that medications such as azithromycin may cause increased heart rate, sympathetic nervous system inhibition, or changes in sweat gland secretion, which will be reflected in heart rate variability and skin conductance. By labeling the effects of drug administration on the autonomic nervous system, we can rule out the possibility of drug side effects being misdiagnosed as psychological stress.
[0041] Specifically, wearable sensors are used to collect heart rate variability (HRV) and electrodermal conductivity (EDS) data from the children, and the collected data is tagged with timestamps and personal information identifiers. Based on the current clinical stage, reference values corresponding to the current stage are obtained from a pre-defined clinical baseline database. These reference values can be obtained through mean or dynamic moving average, representing the fluctuations in physiological indicators caused by treatment or physiological load at the current clinical stage. Assuming the HRV reference value is... The reference value for electrodermal data is ,in Let represent the reference value, and t represent different time points in the current clinical phase. The deviation between real-time data and the reference value at different time points can be expressed as: , ,in Indicates real-time heart rate variability. This represents real-time skin conductance data.
[0042] The offset is obtained by averaging within a sliding window T, and can be expressed as: , , where k is the time index, representing each sampling moment within the preset time window. This represents the deviation between the actual heart rate variability and the corresponding clinical reference value at time k. This means that within a time window T, the heart rate variability offsets at multiple moments are averaged to obtain an estimate of the heart rate variability stability offset at the current moment t. Indicates the number of samples. This means that within a time window T, the heart rate variability offset at multiple moments is averaged to obtain the skin conductance stability offset estimate at the current moment t.
[0043] The deviation compensation factor can be determined as follows: , ,in , This represents the weighting coefficient, which can be dynamically adjusted according to the clinical stage and physiological load. The bias compensation factor representing the heart rate variability. This represents the bias compensation factor for skin conductance.
[0044] Dividing the real-time heart rate variability and skin conductance data by the bias compensation factor respectively, the corrected heart rate variability and skin conductance data can be obtained as follows: , ;in This represents the corrected heart rate variability. This indicates the corrected skin conductance data.
[0045] It should be noted that when new heart rate variability data and skin conductance data are generated, the bias compensation factor is updated by calculating the new average offset in real time.
[0046] It should be noted that heart rate variability is measured via a chest strap and wrist strap psychosensor, while electrodermal data is collected via electrodes.
[0047] In this embodiment, sentiment analysis is performed on the text using natural language processing to obtain a text sentiment vector. Please refer to [link / reference]. Figure 2 The specific content includes:
[0048] Step 21: Obtain the text and preprocess it. Perform word segmentation and part-of-speech tagging on the preprocessed text to identify sentiment keywords, degree adverbs, and negation words. Assume the original text set is... The preprocessed text set is then The preprocessed text is segmented and tagged with parts of speech to identify sentiment keywords, degree adverbs, and negation words, which can be represented as: ,in This is represented by the corresponding part-of-speech tag. Indicates terms. Among them .in Keywords indicating emotions Adverbs of degree Indicates negation.
[0049] Step 22: Generate distance weights based on the semantic distance between negative words and sentiment keywords, apply intensity weights to the basic polarity of sentiment keywords using degree adverbs, and adjust the polarity and intensity of sentiment keywords based on distance weights and intensity weights.
[0050] Specifically, let's assume the basic polarity and intensity of emotional keywords are as follows: The intensity weight corresponding to the degree adverb is The semantic distance between negative words and emotional keywords is: The intensity of emotional keywords can be weighted using degree adverbs as follows: The distance weighting function for the effect of negation words is: ,in Let be the weighting coefficient. Then, adjusting the polarity and intensity of sentiment keywords can be expressed as: Substituting the intensity weights, it can be expressed as: .in Used to characterize the contribution of emotional keywords to the overall emotional state in the current text context.
[0051] This application generates distance weights by obtaining the semantic distance between negative words and emotional keywords, and uses degree adverbs to apply intensity weights to the basic polarity of emotional keywords, thereby achieving joint correction of emotional keywords by degree.
[0052] Step 23: Map the corrected emotion keywords to preset text emotion dimensions and obtain the corresponding values for different emotion dimensions. Define the emotion dimension as... ,in Indicates positive emotions. express , It indicates a neutral emotion. , , ,in Indicates the number of keywords related to emotions. This represents an index of emotion keywords. Indicates the first A key emotion, This represents the adjusted extreme value of emotion. This represents the positive contribution screening function, when Then take the original value, when If the value is 0, then take 0. This represents mapping negative emotions to positive contributions, allowing the intensity of negative emotions to be accumulated. As the value increases, the function value decays rapidly, which can capture situations where emotional words are spoken but the emotion is not strong.
[0053] Step 24: Based on a preset dimensional order, the numerical values corresponding to different emotion dimensions are combined into a structured vector to form a text emotion vector, which represents the emotional state reflected in the text. The preset text emotion dimensions include at least positive, negative, and neutral emotions. The text emotion vector can be represented as: .
[0054] It should be noted that the text data is acquired in real time through interactions with virtual partners, medical staff, or psychological counselors. The text data includes dialogue text, task feedback text, or subjective descriptions of feelings.
[0055] In this embodiment, emotion calculation is performed on text and speech using natural language processing to obtain text emotion vectors and speech emotion vectors. Please refer to [link / reference]. Figure 3 The specific content includes:
[0056] Step 31: After preprocessing the speech, extract the acoustic features of each speech frame. The acoustic features include fundamental frequency features, energy features, spectral features, and speech rate features.
[0057] Step 32: Perform time series analysis on the extracted acoustic features to calculate the changing trend and fluctuation amplitude of the acoustic features in the time dimension.
[0058] Since emotions in speech are typically manifested as a dynamic process that changes over time, rather than a static instantaneous state, this application employs time-series analysis of acoustic features to characterize the evolutionary trend, fluctuation patterns, and stability of speech emotions over time. By performing time-series analysis on multiple acoustic features, including fundamental frequency, energy, spectrum, and speech rate, the arousal level, stability, and changing trends of speech emotions are simultaneously characterized, thus avoiding biases caused by single instantaneous features in judging emotional states. Specifically, fluctuations in fundamental frequency features over time are used to characterize the tension and control state in speech emotions; changes in energy features over time are used to characterize the activation level of the autonomic nervous system; the stability of spectrum features over time is used to identify implicit psychological stress; and changes in speech rate features over time are used to characterize cognitive load and emotion regulation ability. Through time-series analysis of fundamental frequency, energy, spectrum, and speech rate features, a comprehensive expression of the dynamic changes in speech emotions is achieved.
[0059] Specifically, assuming the collected raw speech signal is The effective speech segments after noise reduction and endpoint detection are: ,in Indicates step size, Indicates frame division, This represents the speech frame index. The fundamental frequency feature can be represented as: , Indicates the first Each audio frame in time Discrete speech sample values collected at the location, This represents the time delay; the energy characteristic can be expressed as: , This represents the number of sampling points contained in a single speech frame; the spectral feature can be represented as... The speech rate characteristic can be represented as The acoustic features of the nth frame of speech can then be expressed as: The fundamental frequency fluctuation representing the level of tension can then be expressed as: The energy change can then be expressed as: ,in Then the spectral stability can be expressed as: The change in speech rate can be expressed as: ,in The activation level can be expressed as... Tension can be expressed as... Pleasure level can be expressed as .in , , , , , , , This represents the weighting parameter. This represents the average value of the speech energy features within the current time window. This represents the standard deviation of speech energy features over a time series. This represents the average value of the speech rate characteristics over the current time window. Indicates the degree of fundamental frequency fluctuation. Indicates the dispersion of speech pauses. It represents the standard deviation of speech rate over a time series. This indicates the fundamental frequency stability index. Indicates the continuity of speech.
[0060] Step 33: Obtain the dynamic features of emotion in the speech, map these features to preset speech emotion dimensions, obtain the values corresponding to different emotion dimensions, and combine the values corresponding to different speech emotion dimensions in a preset order to form a speech emotion vector. The preset speech emotion dimensions include at least activation level, tension level, and pleasure level. The speech emotion vector can be represented as follows: .
[0061] It should be noted that the speech signals of the child are collected in real time based on a preset microphone. The speech signals include speech content, speech intensity, and speech rhythm information.
[0062] It should be noted that speech preprocessing includes noise reduction and endpoint detection. Noise reduction is used to obtain clear speech information, while endpoint detection is used to obtain valid speech segments.
[0063] Step 102: Obtain physiological stability indicators based on modified heart rate variability and skin conductance data; obtain cognitive engagement based on eye-tracking data and social interaction records; and obtain social anxiety features based on physiological stability, eye-tracking data, text emotion vectors, and voice emotion vectors.
[0064] It should be noted that eye movement features are acquired through eye movement acquisition devices, and after filtering and standardization, they are used to represent the duration of attention.
[0065] In this embodiment, physiological stability indicators are obtained based on modified heart rate variability and electrodermal data, including: extracting the fluctuation amplitude and rate of change of modified heart rate variability and electrodermal data within adjacent time windows, and constructing physiological stability indicators through weighted combination. When the heart rate variability exhibits low fluctuation characteristics, it indicates high physiological stability; when the heart rate variability exhibits high fluctuation, it indicates an increased level of physiological stress.
[0066] Specifically, the amplitude of the corrected heart rate variability fluctuation within the sliding window. The interior can be represented as: . Display window The mean of the rate of heart rate variability within the heart. The standard deviation of heart rate variability. This represents the compensated heart rate variability data at time index k. This represents the set of time windows ending at the current time t. Indicates time window The number of sampling points contained within.
[0067] The rate of change of corrected skin conductance data within adjacent time windows, in a sliding window The interior can be represented as: . This represents the instantaneous rate of change of electrodermal data. This represents the average value of the rate of change in skin conductance. This indicates the compensated skin conductance data. This represents the set of time windows ending at the current time t. Indicates time window The number of sampling points contained within.
[0068] The physiological stability index constructed by weighted combination can then be expressed as: . , This represents the weighting coefficient.
[0069] In this embodiment of the application, cognitive engagement is obtained based on eye-tracking data and social interaction records, including: obtaining fixation duration and fixation point switching frequency from eye-tracking data to construct attention features; extracting response delay time and task execution step size from interaction data to construct interaction behavior features; fusing attention features and interaction behavior features, and calculating cognitive engagement index by introducing a decay mechanism for response delay.
[0070] Specifically, attention feature extraction is represented as: gaze duration: Frequency of gaze switching: . Indicates the first The duration of each fixation point. Indicates the frequency of gaze switching. Indicates the number of gaze switching. Indicates the duration.
[0071] Interactive behavior features are extracted and represented as: response latency: Task execution step size: The response decays as follows: Then the cognitive engagement level is: .in Operation time point, Indicates the timing of social stimuli. This indicates the number of interaction steps actually completed. This indicates the number of interaction steps expected to be completed. Represents the delay sensitivity coefficient. , This represents the weighting coefficient.
[0072] In this embodiment, social anxiety features are obtained based on physiological stability, eye-tracking data, text emotion vectors, and speech emotion vectors. Specifically, the emotional differences between text emotion vectors and speech emotion vectors are obtained to identify masking features in emotional expression.
[0073] The emotional difference between the text emotion vector and the speech emotion vector is then obtained as follows: .
[0074] By coupling emotional differences with physiological stability indicators and eye movement avoidance characteristics, a social anxiety profile was constructed. When enhanced physiological stress, inconsistent emotional expression, and behavioral avoidance were observed, a significant tendency towards social anxiety was identified.
[0075] The characteristics of eye movement avoidance are: The characteristics of social anxiety are then constructed as follows: . Indicates the proportion of eye contact avoidance. This indicates the total duration of eye contact avoidance. This indicates the total observation time. , , Weight parameters.
[0076] Step 103: Subtract the social anxiety feature from the positive contributions of physiological stability and cognitive engagement, and obtain the psychological adaptation risk index by adjusting for the clinical cycle bias factor, i.e.: ,in , , These are adjustable weights used to balance the importance of different dimensions. This is a clinical cycle deviation factor.
[0077] It should be noted that the clinical cycle deviation factor is obtained based on the child's clinical status parameters at the current moment. The clinical status parameters include at least the position of the treatment cycle, the degree of fatigue, and the level of physiological recovery. The clinical status parameters are mapped to the clinical workload intensity, and the clinical cycle deviation factor is calculated based on the clinical workload intensity. The clinical cycle deviation factor is used to normalize and correct the psychological adaptation risk index, reducing the interference of non-psychological factors on the assessment results.
[0078] Step 104: Predict the gradient of the psychological adaptation risk index change within a preset time period. When the gradient is lower than a preset threshold, map the psychological adaptation risk index and the gradient to augmented reality environment parameters to achieve dynamic matching of psychological states. Please refer to [link / reference]. Figure 4 , specifically:
[0079] Step 41: Within a continuous interaction cycle, obtain the sequence of psychological adaptation risk index of the child within the historical time window.
[0080] Specifically, obtaining information about the child within a historical time window. Internal psychological adaptation risk index sequence ,in Indicates time The obtained psychological adaptation risk index.
[0081] Step 42: Using a preset prediction model, the historical psychological adaptation risk index sequence is used to predict the change in the psychological adaptation risk index within a preset future time period.
[0082] Specifically, based on the risk indices of adjacent points in the historical psychological adaptation risk index sequence, the change sequence of the risk index is obtained: Obtain the instantaneous change sequence: The rate of change represents the trend of psychological adaptation risk over time.
[0083] The instantaneous change sequence is decomposed to obtain trend components and fluctuation components. The trend component is: The fluctuation component is .
[0084] in This indicates the average rate of change in the risk index. It indicates the degree of instability of the change.
[0085] Specifically, within the preset prediction time period Within this framework, the future change in the risk index is predicted based on the trend component and the volatility component. ,in This represents the risk sensitivity coefficient, which amplifies potential risk changes under high volatility conditions. When the value is large, the prediction results exhibit an unstable amplification effect. Describe the length of the prediction time window.
[0086] To avoid prediction results falling outside of physiological or psychological reasonable ranges, boundary constraints are imposed on the prediction results: ,in This indicates the boundary of variation set based on historical statistics or clinical experience. This represents a boundary clipping function that takes the lower limit when the predicted value is less than the lower limit and takes the upper limit when the predicted value is greater than the upper limit.
[0087] Step 43: Based on the predicted amount of change, calculate the gradient of the psychological adaptation risk index over a future preset time period.
[0088] Specifically, the gradient of the psychological adaptation risk index over a future time period can be expressed as: The gradient of change represents the upward or downward trend of psychological adaptation risk within a preset time period.
[0089] Step 44: Compare the changing gradient with a preset threshold. When the changing gradient shows a deteriorating trend, input the current psychological adaptation risk index and the changing gradient into the augmented reality environment parameter space to generate an environment adjustment vector.
[0090] Specifically, the gradient of change is compared with a preset gradient threshold. When the gradient of change is greater than or equal to the preset gradient threshold, it indicates that the child's psychological adaptation status is stable or improving. When the gradient of change is less than the preset gradient threshold, it indicates that the child's psychological adaptation risk is worsening.
[0091] When the gradient of change shows a worsening trend, the current psychological adaptation risk index and the gradient of change are jointly input into the augmented reality environment parameter space to generate an environment adjustment vector, i.e.: The augmented reality environment parameter space includes at least the density of social stimuli, task complexity, interaction rhythm, intensity of visual and auditory feedback, and guidance frequency.
[0092] Step 45: Adjust the augmented reality environment in real time according to the environmental adjustment vector so that the environmental load is dynamically matched with the child's social and psychological adaptability.
[0093] This application predicts the gradient of the psychological adaptation risk index over a future period and maps the gradient of the gradient with the current risk level into augmented reality environment parameters, thereby achieving dynamic matching of the interactive environment with the trend of psychological state changes and avoiding the problem of delayed intervention.
[0094] Step 105: Calculate the emotional correlation value of the psychological adaptation risk index of children with multiple nodes. When the emotional correlation value is at the bottom of the synchronization, insert a common task node, dynamically adjust the augmented reality environment parameters and task difficulty, and realize the establishment of social safety zones and enhanced peer support.
[0095] Specifically, within the same interaction time window, the psychological adaptation risk index of multiple child nodes is obtained: ,in Indicates the first The psychological adaptation risk index of each child at time t is calculated, and emotional feature vectors are obtained synchronously for each node. The emotion feature vector is obtained by fusing the speech emotion vector and the text emotion vector, where is the number of emotion feature vectors.
[0096] Within the preset time window Within this context, calculate the sentiment correlation between any two nodes: ,in Represents a node and nodes The sentiment correlation value. , The standard deviation of the emotion vector.
[0097] Calculate the group sentiment synchronization index based on sentiment correlation value: When the synchronization index is less than the preset synchronization threshold, it is considered to be in a low synchronization state.
[0098] When in a low synchronization state, a common task node is inserted. The task node is completed collaboratively by the children involved in the relevant value calculation. A single node cannot complete the task independently.
[0099] The task difficulty level is dynamically adjusted based on the group's risk status: ,in This represents the average of the multi-node psychological adaptation risk index. As the risk increases, the task difficulty level is automatically adjusted downwards. Indicates the basic difficulty parameter. Indicates the difficulty level of the shared task. The task difficulty adjustment coefficient is described.
[0100] Dynamically adjusting augmented reality environment parameters can be expressed as: ,in , , ,in This indicates the dispersion of the risk index across multiple nodes. All nodes enter the same virtual space, reducing competitive elements in the environment by sharing visual focus and collaborative cues. Represents the visual complexity parameter. Indicates the social intensity parameter, Indicates the interaction rhythm parameter, , , Indicates the initial baseline values for different environmental parameters. , , This represents the environmental regulation coefficient.
[0101] This application calculates the emotional correlation value of the multi-node psychological adaptation risk index. When a low synchronization state is detected, it introduces common task nodes to synchronously adjust the augmented reality environment parameters and task difficulty, thereby achieving dynamic matching between environmental load and group psychological adaptation ability, constructing a stable social safety zone and enhancing peer support.
[0102] Please refer to Figure 5 This application provides a psychosocial adaptation intervention system for adolescent children with malignant tumors, the system comprising:
[0103] The data acquisition module 501 is used to dynamically correct the heart rate variability and skin conductance data according to the current clinical stage, and to perform emotion calculation on text and speech through natural language to obtain text emotion vectors and speech emotion vectors.
[0104] The social anxiety feature acquisition module 502 is used to acquire physiological stability indicators based on modified heart rate variability and skin conductance data, acquire cognitive engagement based on eye movement data and social interaction records, and acquire social anxiety features based on physiological stability, eye movement data, text emotion vectors and voice emotion vectors.
[0105] The psychological adaptation risk index acquisition module 503 is used to subtract social anxiety characteristics from the positive contributions of physiological stability and cognitive participation, and obtain the psychological adaptation risk index through clinical cycle deviation factor correction.
[0106] The psychological state dynamic matching module 504 is used to predict the gradient of the psychological adaptation risk index change within a preset time period in the future. When the gradient of change is lower than a preset threshold, the psychological adaptation risk index and the gradient of change are mapped to augmented reality environment parameters to achieve dynamic matching of psychological states.
[0107] The augmented reality environment parameter dynamic adjustment module 505 is used to calculate the emotional correlation value of the psychological adaptation risk index of children with multiple nodes. When the emotional correlation value is at the bottom synchronization, a common task node is inserted to dynamically adjust the augmented reality environment parameters and task difficulty, thereby realizing the establishment of a social safety zone and enhanced peer support.
[0108] This application obtains social anxiety features based on the child's physiological stability, eye-tracking data, text emotion vectors, and speech emotion vectors; subtracts the social anxiety features from the positive contributions of physiological stability and cognitive engagement, and obtains a psychological adaptation risk index through clinical cycle deviation factor correction; predicts the gradient of the psychological adaptation risk index change within a preset time period, and when the gradient is lower than a preset threshold, maps the psychological adaptation risk index and gradient to augmented reality environment parameters to achieve dynamic matching of psychological state; calculates the emotional correlation value of the psychological adaptation risk index of children at multiple nodes, and inserts a common task node when the emotional correlation value is at a low synchronization, dynamically adjusting the augmented reality environment parameters and task difficulty to establish a social safety zone and enhance peer support. This application conducts psychosocial adaptation intervention based on the child's real-time physical and physiological state, ensuring the timing and intensity of the intervention.
[0109] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.
Claims
1. A psychosocial adaptation intervention method for adolescent children with malignant tumors, characterized in that, include: Based on the current clinical stage, the heart rate variability and skin conductance data are dynamically adjusted, and emotion calculations are performed on text and speech using natural language to obtain text emotion vectors and speech emotion vectors. Physiological stability indicators were obtained based on modified heart rate variability and skin conductance data; cognitive engagement was obtained based on eye-tracking data and social interaction records; and social anxiety features were obtained based on physiological stability, eye-tracking data, text emotion vectors, and voice emotion vectors. The psychological adaptation risk index is obtained by subtracting social anxiety characteristics from the positive contributions of physiological stability and cognitive engagement, and then correcting for clinical cycle deviation factors. Predict the gradient of the psychological adaptation risk index change within a preset time period. When the gradient of change is lower than a preset threshold, map the psychological adaptation risk index and the gradient of change to augmented reality environment parameters to achieve dynamic matching of psychological state. The psychological adaptation risk index of children with multiple nodes is calculated based on emotional correlation. When the emotional correlation value is at the bottom of synchronization, a common task node is inserted, and the parameters of the augmented reality environment and the difficulty of the task are dynamically adjusted to achieve the establishment of a social safe zone and enhanced peer support.
2. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Based on the current clinical stage, heart rate variability and skin conductance data are dynamically adjusted, including: The system collects heart rate variability and skin conductance data in real time, labels the current clinical stage and dosing information, obtains reference values for the corresponding clinical stage from a preset clinical baseline library, calculates the offset between the real-time collected data and the reference values, generates a deviation compensation factor based on the offset, and divides the real-time heart rate variability and skin conductance data by the deviation compensation factor to obtain the corrected heart rate variability and skin conductance data.
3. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, By performing sentiment analysis on text using natural language processing, a text sentiment vector is obtained, including: The text is acquired and preprocessed. The preprocessed text is then segmented and part-of-speech tagged to identify sentiment keywords, degree adverbs, and negation words. Distance weights are generated based on the semantic distance between negative words and sentiment keywords. The basic polarity of sentiment keywords is weighted by degree adverbs. The polarity and intensity of sentiment keywords are then corrected based on the distance weights and intensity weights. Map the corrected emotional keywords to preset text emotional dimensions and obtain the corresponding values for different emotional dimensions; Based on a preset dimensional order, the numerical values corresponding to different emotional dimensions are combined into a structured vector to form a text emotion vector.
4. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Emotional computation is performed on speech using natural language processing to obtain speech emotion vectors, including: After preprocessing the speech, the acoustic features of each speech frame are extracted. Time series analysis is performed on the extracted acoustic features to calculate the changing trend and fluctuation amplitude of the acoustic features over time. The system acquires the dynamic features of emotions in speech, maps these features to preset speech emotion dimensions, obtains the values corresponding to different emotion dimensions, and combines the values corresponding to different speech emotion dimensions in a preset order to form a speech emotion vector.
5. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Physiological stability indicators are obtained based on modified heart rate variability and skin conductance data, including: extracting the fluctuation amplitude and rate of change of modified heart rate variability and skin conductance data in adjacent time windows, and constructing physiological stability indicators by weighted combination.
6. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Cognitive engagement is obtained based on eye-tracking data and social interaction records, including: obtaining fixation duration and fixation point switching frequency from eye-tracking data to construct attention features; extracting response latency and task execution step size from interaction data to construct interaction behavior features; and fusing attention features and interaction behavior features, and calculating cognitive engagement indicators by introducing a decay mechanism for response latency.
7. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Social anxiety features are obtained based on physiological stability, eye-tracking data, text emotion vectors, and speech emotion vectors, including: Obtain the emotional differences between text emotion vectors and speech emotion vectors; By coupling emotional differences with physiological stability indicators and eye movement avoidance characteristics, a social anxiety feature was constructed.
8. The psychosocial adaptation intervention method for adolescent children with malignant tumors according to claim 1, characterized in that, Predict the gradient of psychological adaptation risk index changes over a preset time period. When the gradient falls below a preset threshold, map the psychological adaptation risk index and its gradient to augmented reality environment parameters to achieve dynamic matching of psychological states, including: Within a continuous interaction cycle, the psychological adaptation risk index sequence of the child within a historical time window is obtained. The historical psychological adaptation risk index sequence is then used to predict the change in the psychological adaptation risk index within a future preset time period through a preset prediction model. Based on the predicted change, the change gradient of the psychological adaptation risk index within the future preset time period is calculated. The change gradient is compared with a preset threshold. When the change gradient shows a deteriorating trend, the current psychological adaptation risk index and the change gradient are jointly input into the augmented reality environment parameter space to generate an environment adjustment vector. The augmented reality environment is adjusted in real time according to the environment adjustment vector, so that the environmental load is dynamically matched with the child's social and psychological adaptation ability.
9. A psychosocial adaptation intervention system for adolescent children with malignant tumors, used to implement the methods of claims 1-8, characterized in that, include: The data acquisition module is used to dynamically correct heart rate variability and skin conductance data according to the current clinical stage, and to perform emotion calculations on text and speech through natural language to obtain text emotion vectors and speech emotion vectors. The social anxiety feature acquisition module is used to acquire physiological stability indicators based on modified heart rate variability and skin conductance data, cognitive engagement based on eye movement data and social interaction records, and social anxiety features based on physiological stability, eye movement data, text emotion vectors and voice emotion vectors. The psychological adaptation risk index acquisition module is used to subtract social anxiety characteristics from the positive contributions of physiological stability and cognitive participation, and obtain the psychological adaptation risk index through clinical cycle deviation factor correction. The psychological state dynamic matching module is used to predict the gradient of the psychological adaptation risk index change within a preset time period. When the gradient of change is lower than a preset threshold, the psychological adaptation risk index and the gradient of change are mapped to augmented reality environment parameters to achieve dynamic matching of psychological states. The augmented reality environment parameter dynamic adjustment module is used to calculate the emotional correlation value of the psychological adaptation risk index of children with multiple nodes. When the emotional correlation value is at the bottom synchronization, a common task node is inserted, and the augmented reality environment parameters and task difficulty are dynamically adjusted to realize the establishment of social safety zones and enhanced peer support.
10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-8.